00:00:00 / 00:00:00

Relationship between classification and regression in statistical fairness

By Solenne Gaucher

Appears in collection : Meeting in Mathematical Statistics: Statistical thinking in the age of AI : robustness, fairness and privacy / Rencontre de Statistique Mathématique

Statistical fairness seeks to ensure an equitable distribution of predictions or algorithmic decisions across different sensitive groups. Among the fairness criteria under consideration, demographic parity is arguably the most conceptually straightforward: it simply requires that the distribution of outcomes is identical across all sensitive groups. In this talk, we explore the relationship between classification and regression problems under this constraint. We provide several fundamental characterizations of the optimal classification function under the demographic parity constraint. In the awareness framework, analogous to the classical unconstrained classification scenario, we demonstrate that maximizing accuracy under this fairness constraint is equivalent to solving a fair regression problem followed by thresholding at level 1/2. We extend this result to linear-fractional classification measures (e.g., 𝐹-score, AM measure, balanced accuracy, etc.), emphasizing the pivotal role played by regression in this framework. Our findings leverage the recently developed connection between the demographic parity constraint and the multi-marginal optimal transport formulation. Informally, our result shows that the transition between the unconstrained problem and the fair one is achieved by replacing the conditional expectation of the label by the solution of the fair regression problem. Leveraging our analysis, we also demonstrate an equivalence between the awareness and the unawareness setups for two sensitive groups.

Information about the video

  • Date of recording 21/12/2023
  • Date of publication 08/01/2024
  • Institution CIRM
  • Licence CC BY NC ND
  • Language English
  • Director(s) Luca Recanzone
  • Format MP4

Citation data

  • DOI 10.24350/CIRM.V.20120603
  • Cite this video Gaucher, Solenne (21/12/2023). Relationship between classification and regression in statistical fairness. CIRM. Audiovisual resource. DOI: 10.24350/CIRM.V.20120603
  • URL https://dx.doi.org/10.24350/CIRM.V.20120603

Domain(s)

Bibliography

  • GAUCHER, Solenne, SCHREUDER, Nicolas, et CHZHEN, Evgenii. Fair learning with Wasserstein barycenters for non-decomposable performance measures. In : International Conference on Artificial Intelligence and Statistics. PMLR, 2023. p. 2436-2459. - https://proceedings.mlr.press/v206/gaucher23a.html

Last related questions on MathOverflow

You have to connect your Carmin.tv account with mathoverflow to add question

Ask a question on MathOverflow




Register

  • Bookmark videos
  • Add videos to see later &
    keep your browsing history
  • Comment with the scientific
    community
  • Get notification updates
    for your favorite subjects
Give feedback
Loading…
Loading the web debug toolbar…
Attempt #